Self-organizing feature maps and hidden Markov models for machine-tool monitoring

Vibrations produced by the use of industrial machine tools can contain valuable information about the state of wear of tool cutting edges. However, extracting this information automatically is quite difficult. It has been observed that certain structures present in the vibration patterns are correlated with dullness. We present an approach to extracting features present in these structures using self-organizing feature maps (SOFMs). We have modified the SOFM algorithm in order to improve its generalization abilities and to allow it to better serve as a preprocessor for a hidden Markov model (HMM) classifier. We also discuss the challenge of determining which classes exist in the machining application and introduce an algorithm for automatic clustering of time-sequence patterns using the HMM. We show the success of this algorithm in finding clusters that are beneficial to the machine-monitoring application.

[1]  T.-H. Hou,et al.  Manufacturing process monitoring using neural networks , 1993 .

[2]  David Dornfeld,et al.  Signal Processing for Automatic Supervision , 1994 .

[3]  Padhraic Smyth,et al.  Markov monitoring with unknown states , 1994, IEEE J. Sel. Areas Commun..

[4]  L. Atlas,et al.  Feature extraction networks for dull tool monitoring , 1995, 1995 International Conference on Acoustics, Speech, and Signal Processing.

[5]  Alice M. Agogino,et al.  Real time expert system for predictive diagnostics and control of drilling operation , 1990, Sixth Conference on Artificial Intelligence for Applications.

[6]  Tilo Pfeifer,et al.  Measuring drill wear with digital image processing , 1990 .

[7]  Teuvo Kohonen,et al.  The self-organizing map , 1990 .

[8]  Teuvo Kohonen,et al.  The self-organizing map , 1990, Neurocomputing.

[9]  A.G. Ulsoy,et al.  Applications of adaptive control to machine tool process control , 1989, IEEE Control Systems Magazine.

[10]  Les E. Atlas,et al.  Feature representations for monitoring of tool wear , 1994, Proceedings of ICASSP '94. IEEE International Conference on Acoustics, Speech and Signal Processing.

[11]  David Dornfeld,et al.  Sensor Integration Using Neural Networks for Intelligent Tool Condition Monitoring , 1990 .

[12]  Les E. Atlas,et al.  Bilinear time-frequency representations: new insights and properties , 1993, IEEE Trans. Signal Process..

[13]  D. Haussler,et al.  Hidden Markov models in computational biology. Applications to protein modeling. , 1993, Journal of molecular biology.

[14]  José Carlos Príncipe,et al.  A knowledge-based supervision model for machine tools , 1989, [1989] Proceedings of the Thirteenth Annual International Computer Software & Applications Conference.

[15]  Tony Springall.  Common Principal Components and Related Multivariate Models , 1991 .

[16]  Lane M. D. Owsley,et al.  Automatic clustering of vector time-series for manufacturing machine monitoring , 1997, 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[17]  Robert M. Gray,et al.  An Algorithm for Vector Quantizer Design , 1980, IEEE Trans. Commun..

[18]  Robert M. Gray,et al.  Minimum Cross-Entropy Pattern Classification and Cluster Analysis , 1982, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[19]  J. A. Hartigan,et al.  A k-means clustering algorithm , 1979 .

[20]  Shane Y. Hong.  Self-learning system for knowledge-based diagnoses of drill condition in fully automatic manufacturing system , 1992, Defense, Security, and Sensing.

[21]  Masahiro Fujita,et al.  Analysis of neighborhood interaction in Kohonen neural networks , 1991, [1991] Proceedings. The Fifth International Parallel Processing Symposium.

[22]  Simon Braun,et al.  Signature Analysis Applied to Drilling , 1982 .

[23]  Jenq-Neng Hwang,et al.  A translation/rotation/scaling/occlusion invariant neural network for 2D/3D object classification , 1992, [Proceedings] ICASSP-92: 1992 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[24]  Robert J. Marks,et al.  The use of cone-shaped kernels for generalized time-frequency representations of nonstationary signals , 1990, IEEE Trans. Acoust. Speech Signal Process..

[25]  F. Critchley,et al.  Interval estimation in discrimination: The multivariate normal equal covariance case , 1985 .

[26]  A. Krogh.  Hidden Markov Models in Computational Biology Applications to Protein Modeling UCSC CRL , 1993 .

[27]  A. Galip Ulsoy,et al.  Control of Machining Processes , 1993 .

[28]  Biing-Hwang Juang,et al.  Hidden Markov Models for Speech Recognition , 1991 .

[29]  Luís B. Almeida,et al.  Improving the Learning Speed in Topological Maps of Patterns , 1990 .

[30]  Larry P. Heck,et al.  Mechanical system monitoring using hidden Markov models , 1991, [Proceedings] ICASSP 91: 1991 International Conference on Acoustics, Speech, and Signal Processing.

[31]  Robert U. Ayres,et al.  Complexity, Reliability, and Design: Manufacturing Implications , 1988 .

[32]  David Dornfeld,et al.  Adaptive optimal control of machining process using neural networks , 1991, Proceedings. 1991 IEEE International Conference on Robotics and Automation.

[33]  Allen Gersho,et al.  Vector quantization and signal compression , 1991, The Kluwer international series in engineering and computer science.

[34]  Teuvo Kohonen,et al.  Self-Organization and Associative Memory , 1988 .

[35]  John A. Hartigan,et al.  Clustering Algorithms , 1975 .

[36]  R.J. Fornaro,et al.  A high-performance machine tool controller , 1988, Conference Record of the 1988 IEEE Industry Applications Society Annual Meeting.

[37]  Hossein Hakim,et al.  A comparative study of non-parametric spectral estimators for application in machine vibration analysis , 1992 .

[38]  Les Atlas,et al.  Advantages of cascaded quadratic detectors for analysis of manufacturing sensor data , 1992, [1992] Proceedings of the IEEE-SP International Symposium on Time-Frequency and Time-Scale Analysis.